© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111726
    Prev
    Next
    INDEX
    Explanations

    weave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    1.59
    um
    1.30
     It
    1.28
    ли
    1.07
     not
    1.03
    就
    1.02
    ח
    1.02
    I
    0.99
     hoofd
    0.97
     Not
    0.96
    POSITIVE LOGITS
    -
    1.33
    스
    0.95
    को
    0.91
    speople
    0.90
     인한
    0.88
    {})
    0.88
    )”
    0.87
    {
    0.87
    )?,
    0.87
    skiej
    0.86
    Activations Density 0.000%

    No Known Activations